Src-transformed cells hijack mitosis to extrude from the epithelium

Abstract

At the initial stage of carcinogenesis single mutated cells appear within an epithelium. Mammalian in vitro experiments show that potentially cancerous cells undergo live apical extrusion from normal monolayers. However, the mechanism underlying this process in vivo remains poorly understood. Mosaic expression of the oncogene vSrc in a simple epithelium of the early zebrafish embryo results in extrusion of transformed cells. Here we find that during extrusion components of the cytokinetic ring are recruited to adherens junctions of transformed cells, forming a misoriented pseudo-cytokinetic ring. As the ring constricts, it separates the basal from the apical part of the cell releasing both from the epithelium. This process requires cell cycle progression and occurs immediately after vSrc-transformed cell enters mitosis. To achieve extrusion, vSrc coordinates cell cycle progression, junctional integrity, cell survival and apicobasal polarity. Without vSrc, modulating these cellular processes reconstitutes vSrc-like extrusion, confirming their sufficiency for this process.

Fig. 1

vSrc-transformed cells become apicobasally extruded from the EVL layer. a Experimental design. Fish embryos obtained from a transgenic line expressing tamoxifen-inducible Gal4 specifically in the EVL (Krt18:KalTA4-ERT2) are injected at one-cell stage with constructs encoding oncogenes and effectors/markers under the control of the bi-directional UAS, dUAS. At 50–70% epiboly, embryos are treated with tamoxifen to induce oncogene expression. At tailbud (2–3 h from induction, 10 h post fertilization), embryos are fixed for quantification or mounted in agarose for live-imaging. b Time-lapse imaging of vSrc cell extrusion from the EVL of the zebrafish embryo. Transgenic embryos obtained from a line expressing an RFP-actin marker (red) specifically in the EVL (Krt18:Lifeact-Ruby) line crossed with the Krt18:KalTA4-ERT2 line were injected with the UAS:EGFP-vSrc construct (green). Movies were taken over 4 h. Frames were extracted from a representative movie at indicated times from the tailbud stage (t = 0). White arrowheads indicate cells that become extruded. “1” indicates the cell segmented in c. Scale bar, 30 µm. c Segmented time-lapse images of vSrc cell extrusion. The surface function was used to segment the GFP-positive vSrc cell from b over time using the Imaris software. In this cross section of the embryo (xz view), the cell is undergoing an apicobasal split (apical part extruding outside of the embryo is marked with red arrow and the basal part extruding towards the deep cells with blue arrow). The dashed white line indicates the surface of the embryo. Scale bar, 10 µm. d Quantification of vSrc-mediated cell extrusion type based on time-lapse imaging. Apicobasal extrusion refers to extrusions in which the basal part contains at least a third of the original cell volume. Seven embryos were imaged in seven independent experiments (total number of extrusions: n_Src = 19)

Fig. 2

Contractile Anillin ring is recruited to the lateral cortex prior to extrusion. a, b Quantification of EGFP and EGFP-vSrc cell division (a) and extrusion (b) rates based on time-lapse imaging. Division rates were calculated as the number of divisions over 4 h divided by the initial number of GFP-positive cells per embryo. Each mark represents a division rate in a single embryo. Grey lines represent mean values ± standard deviation (s.d.). Seven embryos were imaged per condition in 14 independent experiments (total number of cells: n_GFP = 121, n_Src = 73). *P < 0.05 (Student’s t-test). c Time-lapse imaging of Anillin-GFP during vSrc cell extrusion. Embryos were injected with the dUAS:myr-Cherry-vSrc;Anillin-GFP construct. Movies were taken over 4 h. Frames were extracted from a representative movie at indicated times where t = 0 is the moment of extrusion. White arrowheads indicate the position of the Anillin ring. Scale bars, 25 µm (xy) 10 µm (xz). d The effect of exogenous Anillin on rescuing the Anillin morphant phenotype cell-autonomously in vSrc-driven extrusion. Embryos were injected with the following constructs: dUAS:EGFP-vSrc and dUAS:EGFP-vSrc,Anillin-GFP and the Anillin morpholino. Data are mean ± s.d. of three independent experiments (total number of embryos: n_Src = 33; n_Src,Anillin = 32). *P < 0.01 (Student’s t-test). e Quantification of the failed extrusion rate based on time-lapse imaging. Embryos were injected with the following constructs: dUAS:EGFP-vSrc;nucGFP and dUAS:EGFP-vSrc;DN-Anillin. Failed extrusion rates were calculated as the number of cells that rounded up and then returned to the monolayer without division or extrusion over 4 h by the initial number of GFP-positive cells per embryo. Each mark represents a division rate in a single embryo. Eleven embryos were imaged per condition in three independent experiments (total number of cells: n_Src = 168, n_{Src,DNAnillin} = 149). Grey lines represent mean values ± s.d. *P < 0.05 (Student’s t-test). f Quantification of the angle between the Anillin ring and the surface of the embryo over time. Data from four cells acquired in three independent experiments were then aligned to the time of extrusion, t = 0, averaged ± s.d. and plotted

Fig. 3

vSrc-transformed cells extrude in early mitosis. a A schematic model of cell cycle regulation. Highlighted in red are the molecules whose roles in cell extrusion were tested in this work. b The effect of Wee1 expression on vSrc-driven extrusion. Embryos were injected with the following constructs: dUAS:EGFP-vSrc and dUAS:EGFP-vSrc;Wee1. Data represent the number of tall and extruded cells divided by the total number of GFP-positive cells. Data are mean ± s.d. of three independent experiments (total number of embryos: n_Src = 21; n_Src,Wee1 = 27). *P < 0.05 (Student’s t-test). c The effect of constitutively active Cdc25 on vSrc-driven extrusion. Embryos were injected with the following constructs: dUAS:EGFP-vSrc and dUAS:EGFP-vSrc;CA-Cdc25. Data are mean ± s.d. of three independent experiments (total number of embryos: n_Src = 18; n_Src,Cdc25 = 21). *P < 0.05 (Student’s t-test). d Constitutively active Cdk1 rescues Wee1 inhibition of vSrc-driven extrusion. Embryos were coinjected with the following constructs: dUAS:EGFP-vSrc alongside either dKrt18:myr-Cherry, dKrt18:Cherry-Wee1 or dKrt18:Cherry-Wee1;CA-Cdk1. Data are mean ± s.d. of three independent experiments (total number of embryos: n_Src = 30; n = 29; n_{Src,Wee1,Cdk1} = 33). *P < 0.05 (Student’s t-test). e Time-lapse imaging of H2B-GFP in mitosis (top panel) and extrusion (bottom panel). Embryos were injected with the dUAS:myr-Cherry-vSrc;H2B-GFP construct. Movies were taken over 4 h and frames were extracted from a representative movie. t = 0 indicates either the beginning of mitosis (chromatin condensation) or the moment of extrusion. Scale bars, 10 µm. f Quantification of the chromatin volume (defined as the volume that H2B-GFP signal occupies in space) measured using the surface function of Imaris. The blue line follows chromatin volume change over time in a dividing EVL cell expressing myr-Cherry (averaged data from 3 cells), the green line—in a dividing vSrc cell (averaged data from 4 cells), the red line—in a extruding vSrc cell (averaged data from five cells). Error bars represent s.d.

Fig. 4

vSrc modulates cell cycle progression. a, b Time-lapse imaging of Cyclin B1-GFP in cell extrusion. Transgenic embryos obtained from a line expressing a cell cycle progression marker specifically in the EVL (Krt18:CcnB1-GFP) crossed with the Krt18:KalTA4-ERT2 line were injected with the construct UAS:myr-Cherry (a) or UAS:myr-Cherry-vSrc (b). Movies were taken over 8 h. Frames were extracted from a representative movie at indicated times from the tailbud stage. White arrowheads indicate cells that undergo mitosis or become extruded. Scale bars, 10 µm. c Length of different cell cycle phases of the EVL cells from the CcnB1-GFP line. The cell cycle phases are defined as follows; M is the time from the nuclear import of CcnB1-GFP until completed cytokinesis; G1/S is the time from completed cytokinesis until the GFP signal returns to the cytoplasm; S/G2/M is the time of the GFP signal present in the cytoplasm until mitosis. Each mark represents a single cell. Black lines represent mean values ± standard deviation (s.d.). Data collected from five movies in three independent experiments. d Mean voxel intensity ± s.d. of the CcnB1-GFP signal in single cells immediately before extrusion (myr-Cherry-vSrc) or division (myr-Cherry). Data collected from 31 extruded vSrc cells and 31 dividing myr-Cherry cells in 12 movies per condition from five independent experiments. ***P = 2.1 × 10⁻⁷ (Student’s t-test), **P = 8.4 × 10⁻⁴ (Student’s t-test). e Cell volume analysis before division and extrusion. Average volume ± s.d. of the cells used for CcnB1-GFP signal quantification immediately before extrusion or division (Fig. 4d). *P < 0.05 (Student’s t-test). f Mean voxel intensity ± s.d. of the green channel (CcnB1-GFP) in myr-Cherry cells and myr-Cherry-vSrc cells at time 0 of a time-lapse from cells remaining in the epithelium. Data collected from 11 embryos per condition in five independent experiments. *P = 0.005 (Student’s t-test)

Fig. 5

Majority of Src-transformed MDCK cells extrude during or instead of mitosis. a The effect of inhibition of the G2/M transition or G1/S transition on extrusion of MDCK-pTR-cSrc-Y527F from a monolayer of normal MDCK cells. Inhibitors 2 mM hydroxyurea or 10 µM Ro-3306 were added with a 9-hour delay after the induction of Src-expression. At 24 h from Src induction cells were fixed, stained with phalloidin and imaged. Data are mean ± s.d. of three independent experiments (total number of cells: n_Ctrl = 155; n_HU = 153; n_Ro3306 = 152). **P < 0.005 (Student’s t-test). b Time-lapse imaging over 24 h of extrusion of MDCK stably expressing both pTR-cSrc-Y527F-GFP and FUCCI. GFP-CAAX labels Src cells (green membrane) that express Cherry-hCdt1 in G1 phase (red nuclei) or mTurquoise-hGEM in S/G2/M phases (green nuclei). c Quantification of the nuclear colour change in MDCK-pTR-cSrc-Y527F-GFP/FUCCI cells during extrusion based on live-imaging. Data are mean ± s.d. of two independent experiments (total number of extruded cells: n = 63)

Fig. 6

vSrc tyrosine kinase modulates cell cycle regulators CDK1 and Pp2a. a A schematic model of Src interference with cell cycle regulation. b Immunofluorescence images of CDK1 pY15 (purple) in the EVL cells expressing the mKO2-CDK1-pep (red) alongside EGFP or EGFP-vSrc (green). Scale bar, 10 µm. c The effect on phosphorylation of CDK1 after 8 h from Src activation in MDCK cells. MM MDCK cells alone, SS Src cells alone, MS cultures mixed 1:1, MM + HU MDCK cells treated with 2 mM hydroxyurea (HU). d Quantification of the mean normalised signal ± s.d. in western blotting with the anti-CDK1-pY15 antibody after 8 h from Src activation in MDCK cells from three independent experiments. **P < 0.005 (Student’s t-test)

Fig. 7

Src-phosphorylated p120-catenin recruits Anillin to the junctions. a The effect of constitutively active and dominant negative RhoA on vSrc-driven extrusion. Embryos were injected with the following constructs: dUAS:EGFP-vSrc, dUAS:EGFP-vSrc;CA-RhoA or dUAS:EGFP-vSrc;DN-RhoA. The two graphs display cells Apically extruded (outside of the embryo) and Tall (within the monolayer but taller than neighbours). Data are mean ± s.d. of 3 independent experiments (total number of embryos: n_Src = 35; n_Src,CA-RhoA = 38; n_Src,DN-RhoA = 36). *P < 0.05 (Student’s t-test). b A schematic model of the domain composition of p120-catenin. In green are phosphorylation sites regulated by the Src kinase (from: PhosphoSitePlus database). In the bottom panel, a design of p120-catenin mutant with two sites regulating the interaction between p120-catenin and RhoA. These sites are mutated from Y to F (p120-mutFF). c The effect of phosphomimetic p120-mutFF on vSrc-driven extrusion. Embryos were injected with the following constructs: dUAS:EGFP-vSrc;p120-wt or dUAS:EGFP-vSrc;p120-mutFF. Data are mean ± s.d. of three independent experiments (total number of embryos: n_Src,p120-wt = 34; n_{Src,p120-mutFF} = 42). *P < 0.05 (Student’s t-test). d, e Time-lapse imaging of the effect of phosphomimetic p120-mutEE on the localisation of Anillin-GFP in cells arrested at the G2/M transition. Embryos were injected with a combination of the following constructs: dUAS:Cherry-Wee1;CA-Cdc25 and dUAS:p120-mutEE;Anillin-GFP. Movies were taken over 4 h. Frames were extracted from a representative movie at indicated times from the tailbud stage in xy (d) and xz (e) view. Scale bars, 40 µm (d) and 20 µm (e). f Time-lapse imaging of Anillin-GFP localisation in cells arrested at the G2/M transition. Embryos were injected with a combination of the following constructs: dUAS:Cherry-Wee1;CA-Cdc25 and dUAS:myr-Cherry;Anillin-GFP. Movies were taken over 4 h. Frames were extracted from a representative movie at indicated times from the tailbud stage. Scale bars, 50 µm. g Time-lapse imaging of the effect of p120-mutFF on the localisation of Anillin-GFP in cells arrested at the G2/M transition. Embryos were injected with a combination of the following constructs: dUAS:Cherry-Wee1;CA-Cdc25 and dUAS:p120-mutFF;Anillin-GFP. Movies were taken over 4 h. Frames were extracted from a representative movie at indicated times from the tailbud stage. Scale bars, 25 µm

Fig. 8

vSrc modulates apical polarity complex to facilitate extrusion. a A schematic model of regulation of apicobasal polarity by Cdc42 (adapted from ref.). The Par3-Par6-aPKC complex is recruited to the cell surface in a Par3-dependent manner, and is regulated by apically localised Cdc42. Active Cdc42 stimulates phosphorylation, dissociation and relocation of Par3 to the apical-lateral border at tight junctions (TJ), while Par6-aPKC moves apically to define the apical domain^,,. b The effect of dominant negative aPKC on vSrc-driven extrusion. Embryos were injected with the following constructs: dUAS:EGFP-vSrc and dUAS:EGFP-vSrc;DN-aPKC. Data are mean ± s.d. of three independent experiments (total number of embryos: n_Src = 31; n_Src,DN-aPKC = 31). *P < 0.05 (Student’s t-test). c The effect of dominant negative Par3 on vSrc-driven extrusion. Embryos were injected with the following constructs: dUAS:EGFP-vSrc and dUAS:EGFP-vSrc;DN-Par3. Data are mean ± s.d. of three independent experiments (total number of embryos: n_Src = 36; n_Src,DN-Par3 = 34). *P < 0.01 (Student’s t-test). d The effect of overexpression of WASP-RBD-GFP on vSrc-driven extrusion. Embryos were injected with the following constructs: dUAS:EGFP-vSrc and dUAS:EGFP-vSrc;WASP-RBD-GFP. Data are mean ± s.d. of three independent experiments (total number of embryos: n_Src = 31; n_{Src,WASP-RBD-GFP} = 36). *P < 0.01 (Student’s t-test). e The effect of phosphomimetic aPKC-Y417F on vSrc-driven extrusion. Embryos were injected with the following constructs: dUAS:EGFP-vSrc;aPKC-wt or dUAS:EGFP-vSrc;aPKC-Y417F. Data are mean ± s.d. of three independent experiments (total number of embryos: n_Src,aPKC-wt = 39; n_{Src,aPKC-Y417F} = 42). *P < 0.05 (Student’s t-test)

Fig. 9

Modulating the cell cycle, junctions and polarity mimics vSrc-like extrusion. a Time-lapse imaging of vSrc-like extrusion induced by coexpression of p120-mutEE, aPKC-delN and the apoptotic inhibitor XIAP in G2/M-arrested cells. Embryos were injected with a combination of the following constructs: dUAS:Cherry-Wee1;CA-Cdc25, dUAS:p120-mutFF;aPKC-delN and Krt18:XIAP. Movies were taken over 6 h. Frames were extracted from a representative movie at indicated times from the tailbud stage. The cell is undergoing an apicobasal split (apical part is marked with red arrows and the basal part with blue arrows). Scale bars, 15 µm. b Time-lapse imaging of vSrc-like cell extrusion in a segmented using the Imaris software. The surface function was used to segment GFP-positive cells over time. In this cross section of the embryo (xz view), the cell is undergoing an apicobasal split (apical part is marked with red arrows and the basal part with blue arrows). The dashed white line indicates the surface of the embryo. Scale bars, 10 µm. c Quantification of the type of vSrc-like cell extrusion based on time-lapse imaging. Extrusion was induced by coexpression of p120-mutEE, aPKC-delN and the apoptotic inhibitor XIAP in G2/M-arrested cells. Fourteen embryos were imaged in four independent experiments (total number of extrusions: n_{p120EE,aPKC-delN,wee1,cdc25,XIAP} = 27). d A schematic model of vSrc-driven cell extrusion. vSrc interferes with the cell cycle, and modulates adherens junctions, cell survival and apicobasal polarity, leading to apicobasal extrusion. vSrc-expressing cell becomes taller than its neighbours. Cell cycle regulators are hijacked; Pp2A is inactivated earlier in the cell cycle, but counteracting Cdk1 inhibition results in G2/M arrest instead of mitosis. The nuclear envelope becomes partially permeable and Anillin is recruited to the adherens junctions by modified p120-catenin, presumably through active RhoA. A contractile junctional ring assembles parallel to the plane of the epithelium, constricts in early mitosis and releases the cell from the epithelium. vSrc-mediated modulation of the apicobasal polarity complex (e.g. aPKC) promotes the predominantly apical direction of extrusion. Immediate cell death is avoided due to vSrc promoting cell survival